Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to conflicts or debates

    oai_token-act-pair · gpt-3.5-turbo

    significant themes of struggle and achievement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eston
    -0.73
    eka
    -0.70
     Higher
    -0.67
    ridor
    -0.67
    iframe
    -0.66
    hua
    -0.64
    resh
    -0.64
    EStream
    -0.64
    odcast
    -0.63
     Howell
    -0.63
    POSITIVE LOGITS
     imaginable
    1.13
     except
    1.04
     hoop
    0.83
     crap
    0.80
     fuss
    0.74
     nodd
    0.73
     facets
    0.72
     attendant
    0.72
     stuff
    0.72
    except
    0.70
    Act Density 0.230%

    No Known Activations